{"id":"https://openalex.org/W2946554390","doi":"https://doi.org/10.1109/iros40897.2019.8968149","title":"Hierarchical Reinforcement Learning for Concurrent Discovery of Compound and Composable Policies","display_name":"Hierarchical Reinforcement Learning for Concurrent Discovery of Compound and Composable Policies","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2946554390","doi":"https://doi.org/10.1109/iros40897.2019.8968149","mag":"2946554390"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8968149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.09668","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084329458","display_name":"Domingo Esteban","orcid":"https://orcid.org/0000-0002-3134-0281"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Domingo Esteban","raw_affiliation_strings":["Istituto Italiano di Tecnologia,Department of Advanced Robotics,Genova,Italy,16163","[Istituto Italiano di Tecnologia]"],"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia,Department of Advanced Robotics,Genova,Italy,16163","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"[Istituto Italiano di Tecnologia]","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063761733","display_name":"Leonel Rozo","orcid":"https://orcid.org/0000-0001-5970-9135"},"institutions":[{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE","IT"],"is_corresponding":false,"raw_author_name":"Leonel Rozo","raw_affiliation_strings":["Bosch Center for Artificial Intelligence,Renningen,Germany,71272","[Istituto Italiano di Tecnologia]"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence,Renningen,Germany,71272","institution_ids":["https://openalex.org/I889804353"]},{"raw_affiliation_string":"[Istituto Italiano di Tecnologia]","institution_ids":["https://openalex.org/I30771326"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044243940","display_name":"Darwin G. Caldwell","orcid":"https://orcid.org/0000-0002-6233-9961"},"institutions":[{"id":"https://openalex.org/I4210145457","display_name":"Robert Bosch (Taiwan)","ror":"https://ror.org/046as2g47","country_code":"TW","type":"company","lineage":["https://openalex.org/I4210145457","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I30771326","display_name":"Italian Institute of Technology","ror":"https://ror.org/042t93s57","country_code":"IT","type":"facility","lineage":["https://openalex.org/I30771326"]}],"countries":["IT","TW"],"is_corresponding":false,"raw_author_name":"Darwin G. Caldwell","raw_affiliation_strings":["Istituto Italiano di Tecnologia,Department of Advanced Robotics,Genova,Italy,16163","Robert Bosch GmBH"],"affiliations":[{"raw_affiliation_string":"Istituto Italiano di Tecnologia,Department of Advanced Robotics,Genova,Italy,16163","institution_ids":["https://openalex.org/I30771326"]},{"raw_affiliation_string":"Robert Bosch GmBH","institution_ids":["https://openalex.org/I4210145457"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084329458"],"corresponding_institution_ids":["https://openalex.org/I30771326"],"apc_list":null,"apc_paid":null,"fwci":0.2893,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65408674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1818","last_page":"1825"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8181638717651367},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7268065810203552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5626134872436523},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5622600317001343},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5602824687957764},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5569957494735718},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4716857075691223},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4252830743789673},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34596168994903564},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3396434485912323},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09221789240837097},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08392813801765442}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8181638717651367},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7268065810203552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5626134872436523},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5622600317001343},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5602824687957764},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5569957494735718},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4716857075691223},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4252830743789673},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34596168994903564},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3396434485912323},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09221789240837097},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08392813801765442},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros40897.2019.8968149","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.09668","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.09668","pdf_url":"https://arxiv.org/pdf/1905.09668","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2946554390","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1905.09668.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1905.09668","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1905.09668","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.09668","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.09668","pdf_url":"https://arxiv.org/pdf/1905.09668","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2946554390.pdf","grobid_xml":"https://content.openalex.org/works/W2946554390.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W64088143","https://openalex.org/W72400652","https://openalex.org/W567721252","https://openalex.org/W1592847719","https://openalex.org/W1976126972","https://openalex.org/W1987725948","https://openalex.org/W2029722408","https://openalex.org/W2111967991","https://openalex.org/W2132622533","https://openalex.org/W2144576818","https://openalex.org/W2168342951","https://openalex.org/W2551887912","https://openalex.org/W2619268125","https://openalex.org/W2772044689","https://openalex.org/W2791797404","https://openalex.org/W2793351326","https://openalex.org/W2799151646","https://openalex.org/W2889939141","https://openalex.org/W2904246096","https://openalex.org/W2905567628","https://openalex.org/W2913060459","https://openalex.org/W2962864381","https://openalex.org/W2963403593","https://openalex.org/W2963864421","https://openalex.org/W2964118020","https://openalex.org/W2964161785","https://openalex.org/W4211219629","https://openalex.org/W6602868551","https://openalex.org/W6616173779","https://openalex.org/W6644042570","https://openalex.org/W6676560026","https://openalex.org/W6679365036","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6729556111","https://openalex.org/W6738370996","https://openalex.org/W6740888197","https://openalex.org/W6747473740","https://openalex.org/W6748523217","https://openalex.org/W6749479297","https://openalex.org/W6750186571","https://openalex.org/W6757592117"],"related_works":["https://openalex.org/W3004094900","https://openalex.org/W2112401277","https://openalex.org/W57282082","https://openalex.org/W2945794705","https://openalex.org/W1726275262","https://openalex.org/W3080901109","https://openalex.org/W2617832762","https://openalex.org/W2788519588","https://openalex.org/W2949604932","https://openalex.org/W298069310","https://openalex.org/W2768663371","https://openalex.org/W3009245728","https://openalex.org/W2789102901","https://openalex.org/W2786122328","https://openalex.org/W2513373085","https://openalex.org/W778742492","https://openalex.org/W2911679928","https://openalex.org/W2920329255","https://openalex.org/W1546054412","https://openalex.org/W3213484318"],"abstract_inverted_index":{"A":[0],"common":[1,46],"strategy":[2],"to":[3,15,27,61,94,104,113,179,203,210],"deal":[4],"with":[5,196],"the":[6,41,66,70,96,133,139,155,161,166,183,189,193,197,205],"expensive":[7],"reinforcement":[8],"learning":[9,51,67,148,157,184],"(RL)":[10],"of":[11,21,69,79,108,119,132,138,188],"complex":[12,71,125,206],"tasks":[13,91],"is":[14,82,87,129,171],"decompose":[16],"them":[17],"into":[18],"a":[19,38,106,117,124,130,174],"collection":[20],"subtasks":[22,97,115],"that":[23,92,128,192,215],"are":[24],"usually":[25,83],"simpler":[26],"learn":[28],"as":[29,31],"well":[30],"reusable":[32],"for":[33,43,90,147],"new":[34],"problems.":[35],"However,":[36],"when":[37],"robot":[39],"learns":[40],"policies":[42,59,74,81,111,153,214],"these":[44,56,114],"subtasks,":[45],"approaches":[47],"treat":[48],"every":[49],"policy":[50,127,199],"process":[52,68,158],"separately.":[53],"Therefore,":[54],"all":[55],"individual":[57,80],"(composable)":[58],"need":[60],"be":[62],"learned":[63],"before":[64],"tackling":[65],"task":[72,207],"through":[73],"composition.":[75],"Moreover,":[76,142],"such":[77],"composition":[78],"performed":[84],"sequentially,":[85],"which":[86],"not":[88,201],"suitable":[89],"require":[93],"perform":[95,217],"concurrently.":[98],"In":[99],"this":[100],"paper,":[101],"we":[102,143],"propose":[103,144],"combine":[105],"set":[107,118],"composable":[109,140,152,213],"Gaussian":[110,126],"corresponding":[112,220],"using":[116],"activation":[120],"vectors,":[121],"resulting":[122],"in":[123,218],"function":[131],"means":[134],"and":[135,151],"covariances":[136],"matrices":[137],"policies.":[141],"an":[145],"algorithm":[146,170],"both":[149],"compound":[150,167,198],"within":[154],"same":[156],"by":[159],"exploiting":[160],"off-policy":[162],"data":[163],"generated":[164],"from":[165],"policy.":[168],"The":[169,186],"built":[172],"on":[173],"maximum":[175],"entropy":[176],"RL":[177],"approach":[178],"favor":[180],"exploration":[181],"during":[182],"process.":[185],"results":[187],"experiments":[190],"show":[191],"experience":[194],"collected":[195],"permits":[200],"only":[202],"solve":[204],"but":[208],"also":[209],"obtain":[211],"useful":[212],"successfully":[216],"their":[219],"subtasks.":[221]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}